PB
Pratik Prabhanjan Brahma
cs.AIcs.CLcs.CVcs.LGcond-mat.mtrl-scicond-mat.stat-mechcond-mat.dis-nncond-mat.mes-hallcond-mat.str-elcs.RO
On Valency
published · living versionsW_zdks3phy·v1 · currentpublished
AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization
with Ji Liu, Saptarshi Majumder, Yiqing Huang, Wenwen Ouyang +12
1 version
Preprints & journals
17 papers in the corpus · 2015–2026AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization2609.12471v1 · Ji Liu, Saptarshi Majumder, Yiqing Huang et al.2026 · 0 citationsarXivon Valency
Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion2606.00616v3 · Shivam Singh, Saptarshi Majumder, Pratik Prabhanjan Brahma et al.2026 · 0 citationsarXiv
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference2602.18846v2 · Aditya Kumar Singh, Hitesh Kandala, Pratik Prabhanjan Brahma et al.2026 · 0 citationsarXiv
AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection2602.11931v2 · Pretam Ray, Pratik Prabhanjan Brahma, Zicheng Liu et al.2026 · 0 citationsarXiv
Hardware Acceleration of Frustrated Lattice Systems using Convolutional Restricted Boltzmann Machine2511.20911v1 · Pratik Brahma, Junghoon Han, Tamzid Razzaque et al.2025 · 0 citationsarXiv
Instella: Fully Open Language Models with Stellar Performance2511.10628v2 · Jiang Liu, Jialian Wu, Xiaodong Yu et al.2025 · 0 citationsarXiv
Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks2507.23194v1 · Jianghui Wang, Vinay Joshi, Saptarshi Majumder et al.2025 · 0 citationsarXiv
SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers2507.20527v3 · Chaitanya Manem, Pratik Prabhanjan Brahma, Prakamya Mishra et al.2025 · 0 citationsarXiv
TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering2506.04642v1 · Vinay Joshi, Pratik Prabhanjan Brahma, Zicheng Liu et al.2025 · 0 citationsarXiv
Emergent Classical Spin Liquid Phases in an Ising Lattice via Size Effects2310.06244v1 · Pratik Brahma, Sayeef Salahuddin2023 · 1 citationarXiv
Accelerated Modelling of Interfaces for Electronic Devices using Graph Neural Networks2310.06995v1 · Pratik Brahma, Krishnakumar Bhattaram, Sayeef Salahuddin2023 · 0 citationsarXiv
Topological Edge Conduction Induced by Strong Anisotropic Exchange Interactions2212.08316v1 · Shehrin Sayed, Pratik Brahma, Cheng-Hsiang Hsu et al.2022 · 1 citationarXiv
Single Shot Multitask Pedestrian Detection and Behavior Prediction2101.02232v1 · Prateek Agrawal, Pratik Prabhanjan Brahma2021 · 2 citationsarXiv
Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction1907.10178v1 · Luca Anthony Thiede, Pratik Prabhanjan Brahma2019 · 65 citationsarXiv
Structured Memory based Deep Model to Detect as well as Characterize Novel Inputs1801.09859v1 · Pratik Prabhanjan Brahma, Qiuyuan Huang, Dapeng Wu2018 · 1 citationarXiv
Reinforced Robust Principal Component Pursuit.28320678 · Brahma, Pratik Prabhanjan, She, Yiyuan, Li, Shijie et al.2019 · 22 citationsIEEE transactions on neural networks and learning systems. 2018;29(5):1525-1538
Why Deep Learning Works: A Manifold Disentanglement Perspective.26672049 · Brahma, Pratik Prabhanjan, Wu, Dapeng, She, Yiyuan2017 · 190 citationsIEEE transactions on neural networks and learning systems. 2016;27(10):1997-2008
Career total: 25 works. 17 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.